Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 5 papers
Filter3

System type

AI Agent3

Layer

Application layer3

System component

MCP and skills4Memory1RAG4Guardrails and judges8Monitors3Reasoning chains13Permissions and sandboxing3Fine-tuning and open weights4Vision4Image generation1Multimodal6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
System component：MemorySystem component：MonitorsSystem component：Image generationClear all

Another 254papers do not have category tags yet and are not included in filtered results.

  2. Analysis and theoryarXiv 2609.37312

    研究：隐蔽推理必然留下信息痕迹，但思维链未必可读

    分析隐蔽推理在思维链监控下的信息足迹下界与不可读性

    arXiv
    2609.37312
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, Qwen 3.5 397B-A17B and others12

    Abstract论文从理论与实证探明了思维链监控的边界：复杂隐蔽计算必然泄露信息足迹且需承担长度税，但该足迹可被在线加密而不可读。

    Paper analysisRead analysis
  3. Analysis and theoryarXiv 2609.32390

    基于 2026 年 Hugging Face 事件的奖励作弊与 Agent 围堵失效蒙特卡洛研究

    用五阶段蒙特卡洛分析奖励作弊如何导致 Agent 围堵失效

    arXiv
    2609.32390
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Abstract分层控制的模拟事件率低于弱控制以及单独隔离或单独监控。

    这项研究用蒙特卡洛把奖励黑客接到外部安全事件上，比较的是控制组合，不是 Hugging Face 事件的再现概率。

    Paper analysisRead analysis
  4. Analysis and theoryarXiv 2609.07162

    论文：LLM 安全监控的监督缺口并非能力问题

    刻画单迹监控对跨执行超性质的监督缺口

    arXiv
    2609.07162
    Published
    Layer
    Application layer
    Setting
    LLM applications, AI Agent
    Evaluated models
    Llama-3.1-8B, Mistral-24B, GPT-4o-mini and others9
    Abstract单迹监督的上界由 TV 决定。

    论文测量单迹安全监控相对 2-safety 超性质能看见多少：跨租户泄漏、觉察到被评估、策略性表现不佳都由两次执行之差定义，一条轨迹装不下判定。

    Paper analysisRead analysis
  5. Analysis and theoryarXiv 2608.27924

    智能体记忆如何可靠处理不可回答问题：一项系统研究

    分析外部记忆对智能体处理不可回答问题的影响

    arXiv
    2608.27924
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    DeepSeek-V3.2, Qwen3-235B-A22B-Instruct-2507, GPT-5.5
    Abstract记忆能选择性提高 UAQ 的可接受回应，但跨数据集不稳定，且更依赖可迁移的行为指导。

    这份研究在同一智能体框架里检查外部记忆会不会让不可回答问题的处理更稳，以及稳来自哪一种存储内容。

    Paper analysisRead analysis
You have reached the end